Rental listing New York city map

library(jsonlite)
library(dplyr)
library(ggplot2)
library(magrittr)
library(ggmap)
library(knitr)

KAGGLE <- TRUE
train_path <- ifelse(KAGGLE, "../input/train.json", "data/train.json")
training <- fromJSON(train_path) %>% bind_rows 
# Keep list variables 
features <- training$features
photos <- training$photos
# Remove list variables from data
training$features <- NULL
training$photos <- NULL 
# Convert to data.frame
training <- sapply(training, unlist) %>%
  data.frame(., stringsAsFactors = FALSE)
# Add removed variables
training$features <- features
training$photos <- photos
# Clean memory
rm(features)
rm(photos)

numerical_variables <- c("bathrooms", "bedrooms", "longitude", "latitude", "price")
training[, numerical_variables] %<>% lapply(., as.numeric)
training$interest_level <- as.factor(training$interest_level)

# New York City Center Coords
ny_lat <- 40.785091; ny_lon <- -73.968285
# Alternate New York City Center Coords
ny_center <- geocode("new york", source = "google")
ny_center

# Add Euclidean Distance to City Center
training$distance_city <- mapply(
      function(lon, lat) sqrt((lon - ny_lon)^2  + (lat - ny_lat)^2), 
      training$longitude, training$latitude) 

# Discard real state far from City Center
ny_outliners_dist <- 0.2
ggplot(training[training$distance_city < ny_outliners_dist, ], 
       aes(distance_city, color = interest_level)) + geom_density()

# Discard real state far from City Center
ggplot(training, aes(log(distance_city), color = interest_level)) + 
      geom_density()

map <- get_googlemap(zoom = 12,
  # Use Alternate New York City Center Coords
  center = ny_center %>% as.numeric,
  maptype = "satellite", sensor = FALSE)

p <- ggmap(map) + 
      geom_point(size = 1, data = training, 
                 aes(x = longitude, y = latitude, color = interest_level)) + 
      facet_grid(facets = . ~ interest_level, scales = "free", space = "free") +
      xlab("") + ylab("") + scale_colour_brewer(palette = "Set1")
p

outliers_addrs <- training[training$longitude == 0 | 
                                 training$latitude == 0, ]$street_address
outliers_addrs

# addresses are supposed to be in nyc
outliers_ny <- paste(outliers_addrs, ", new york")
# search for geological location from google
outliers_addrs <- data.frame("street_address" = outliers_addrs)
coords <- sapply(outliers_ny,
                 function(x) geocode(x, source = "google")) %>%
  t %>%
  data.frame %>%
  cbind(outliers_addrs, .)
rownames(coords) <- 1:nrow(coords)
# Display table
kable(coords)

training[training$longitude == 0,]$longitude <- coords$lon
training[training$latitude == 0,]$latitude <- coords$lat